linux/Documentation/filesystems/proc.txt
<<
>>
Prefs
   1------------------------------------------------------------------------------
   2                       T H E  /proc   F I L E S Y S T E M
   3------------------------------------------------------------------------------
   4/proc/sys         Terrehon Bowden <terrehon@pacbell.net>        October 7 1999
   5                  Bodo Bauer <bb@ricochet.net>
   6
   72.4.x update      Jorge Nerin <comandante@zaralinux.com>      November 14 2000
   8move /proc/sys    Shen Feng <shen@cn.fujitsu.com>                 April 1 2009
   9------------------------------------------------------------------------------
  10Version 1.3                                              Kernel version 2.2.12
  11                                              Kernel version 2.4.0-test11-pre4
  12------------------------------------------------------------------------------
  13fixes/update part 1.1  Stefani Seibold <stefani@seibold.net>       June 9 2009
  14
  15Table of Contents
  16-----------------
  17
  18  0     Preface
  19  0.1   Introduction/Credits
  20  0.2   Legal Stuff
  21
  22  1     Collecting System Information
  23  1.1   Process-Specific Subdirectories
  24  1.2   Kernel data
  25  1.3   IDE devices in /proc/ide
  26  1.4   Networking info in /proc/net
  27  1.5   SCSI info
  28  1.6   Parallel port info in /proc/parport
  29  1.7   TTY info in /proc/tty
  30  1.8   Miscellaneous kernel statistics in /proc/stat
  31  1.9   Ext4 file system parameters
  32
  33  2     Modifying System Parameters
  34
  35  3     Per-Process Parameters
  36  3.1   /proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj - Adjust the oom-killer
  37                                                                score
  38  3.2   /proc/<pid>/oom_score - Display current oom-killer score
  39  3.3   /proc/<pid>/io - Display the IO accounting fields
  40  3.4   /proc/<pid>/coredump_filter - Core dump filtering settings
  41  3.5   /proc/<pid>/mountinfo - Information about mounts
  42  3.6   /proc/<pid>/comm  & /proc/<pid>/task/<tid>/comm
  43  3.7   /proc/<pid>/task/<tid>/children - Information about task children
  44  3.8   /proc/<pid>/fdinfo/<fd> - Information about opened file
  45  3.9   /proc/<pid>/map_files - Information about memory mapped files
  46  3.10  /proc/<pid>/timerslack_ns - Task timerslack value
  47
  48  4     Configuring procfs
  49  4.1   Mount options
  50
  51------------------------------------------------------------------------------
  52Preface
  53------------------------------------------------------------------------------
  54
  550.1 Introduction/Credits
  56------------------------
  57
  58This documentation is  part of a soon (or  so we hope) to be  released book on
  59the SuSE  Linux distribution. As  there is  no complete documentation  for the
  60/proc file system and we've used  many freely available sources to write these
  61chapters, it  seems only fair  to give the work  back to the  Linux community.
  62This work is  based on the 2.2.*  kernel version and the  upcoming 2.4.*. I'm
  63afraid it's still far from complete, but we  hope it will be useful. As far as
  64we know, it is the first 'all-in-one' document about the /proc file system. It
  65is focused  on the Intel  x86 hardware,  so if you  are looking for  PPC, ARM,
  66SPARC, AXP, etc., features, you probably  won't find what you are looking for.
  67It also only covers IPv4 networking, not IPv6 nor other protocols - sorry. But
  68additions and patches  are welcome and will  be added to this  document if you
  69mail them to Bodo.
  70
  71We'd like  to  thank Alan Cox, Rik van Riel, and Alexey Kuznetsov and a lot of
  72other people for help compiling this documentation. We'd also like to extend a
  73special thank  you to Andi Kleen for documentation, which we relied on heavily
  74to create  this  document,  as well as the additional information he provided.
  75Thanks to  everybody  else  who contributed source or docs to the Linux kernel
  76and helped create a great piece of software... :)
  77
  78If you  have  any comments, corrections or additions, please don't hesitate to
  79contact Bodo  Bauer  at  bb@ricochet.net.  We'll  be happy to add them to this
  80document.
  81
  82The   latest   version    of   this   document   is    available   online   at
  83http://tldp.org/LDP/Linux-Filesystem-Hierarchy/html/proc.html
  84
  85If  the above  direction does  not works  for you,  you could  try the  kernel
  86mailing  list  at  linux-kernel@vger.kernel.org  and/or try  to  reach  me  at
  87comandante@zaralinux.com.
  88
  890.2 Legal Stuff
  90---------------
  91
  92We don't  guarantee  the  correctness  of this document, and if you come to us
  93complaining about  how  you  screwed  up  your  system  because  of  incorrect
  94documentation, we won't feel responsible...
  95
  96------------------------------------------------------------------------------
  97CHAPTER 1: COLLECTING SYSTEM INFORMATION
  98------------------------------------------------------------------------------
  99
 100------------------------------------------------------------------------------
 101In This Chapter
 102------------------------------------------------------------------------------
 103* Investigating  the  properties  of  the  pseudo  file  system  /proc and its
 104  ability to provide information on the running Linux system
 105* Examining /proc's structure
 106* Uncovering  various  information  about the kernel and the processes running
 107  on the system
 108------------------------------------------------------------------------------
 109
 110
 111The proc  file  system acts as an interface to internal data structures in the
 112kernel. It  can  be  used to obtain information about the system and to change
 113certain kernel parameters at runtime (sysctl).
 114
 115First, we'll  take  a  look  at the read-only parts of /proc. In Chapter 2, we
 116show you how you can use /proc/sys to change settings.
 117
 1181.1 Process-Specific Subdirectories
 119-----------------------------------
 120
 121The directory  /proc  contains  (among other things) one subdirectory for each
 122process running on the system, which is named after the process ID (PID).
 123
 124The link  self  points  to  the  process reading the file system. Each process
 125subdirectory has the entries listed in Table 1-1.
 126
 127
 128Table 1-1: Process specific entries in /proc
 129..............................................................................
 130 File           Content
 131 clear_refs     Clears page referenced bits shown in smaps output
 132 cmdline        Command line arguments
 133 cpu            Current and last cpu in which it was executed   (2.4)(smp)
 134 cwd            Link to the current working directory
 135 environ        Values of environment variables
 136 exe            Link to the executable of this process
 137 fd             Directory, which contains all file descriptors
 138 maps           Memory maps to executables and library files    (2.4)
 139 mem            Memory held by this process
 140 root           Link to the root directory of this process
 141 stat           Process status
 142 statm          Process memory status information
 143 status         Process status in human readable form
 144 wchan          Present with CONFIG_KALLSYMS=y: it shows the kernel function
 145                symbol the task is blocked in - or "0" if not blocked.
 146 pagemap        Page table
 147 stack          Report full stack trace, enable via CONFIG_STACKTRACE
 148 smaps          an extension based on maps, showing the memory consumption of
 149                each mapping and flags associated with it
 150 numa_maps      an extension based on maps, showing the memory locality and
 151                binding policy as well as mem usage (in pages) of each mapping.
 152..............................................................................
 153
 154For example, to get the status information of a process, all you have to do is
 155read the file /proc/PID/status:
 156
 157  >cat /proc/self/status
 158  Name:   cat
 159  State:  R (running)
 160  Tgid:   5452
 161  Pid:    5452
 162  PPid:   743
 163  TracerPid:      0                                             (2.4)
 164  Uid:    501     501     501     501
 165  Gid:    100     100     100     100
 166  FDSize: 256
 167  Groups: 100 14 16
 168  VmPeak:     5004 kB
 169  VmSize:     5004 kB
 170  VmLck:         0 kB
 171  VmHWM:       476 kB
 172  VmRSS:       476 kB
 173  RssAnon:             352 kB
 174  RssFile:             120 kB
 175  RssShmem:              4 kB
 176  VmData:      156 kB
 177  VmStk:        88 kB
 178  VmExe:        68 kB
 179  VmLib:      1412 kB
 180  VmPTE:        20 kb
 181  VmSwap:        0 kB
 182  HugetlbPages:          0 kB
 183  Threads:        1
 184  SigQ:   0/28578
 185  SigPnd: 0000000000000000
 186  ShdPnd: 0000000000000000
 187  SigBlk: 0000000000000000
 188  SigIgn: 0000000000000000
 189  SigCgt: 0000000000000000
 190  CapInh: 00000000fffffeff
 191  CapPrm: 0000000000000000
 192  CapEff: 0000000000000000
 193  CapBnd: ffffffffffffffff
 194  NoNewPrivs:     0
 195  Seccomp:        0
 196  voluntary_ctxt_switches:        0
 197  nonvoluntary_ctxt_switches:     1
 198
 199This shows you nearly the same information you would get if you viewed it with
 200the ps  command.  In  fact,  ps  uses  the  proc  file  system  to  obtain its
 201information.  But you get a more detailed  view of the  process by reading the
 202file /proc/PID/status. It fields are described in table 1-2.
 203
 204The  statm  file  contains  more  detailed  information about the process
 205memory usage. Its seven fields are explained in Table 1-3.  The stat file
 206contains details information about the process itself.  Its fields are
 207explained in Table 1-4.
 208
 209(for SMP CONFIG users)
 210For making accounting scalable, RSS related information are handled in an
 211asynchronous manner and the value may not be very precise. To see a precise
 212snapshot of a moment, you can see /proc/<pid>/smaps file and scan page table.
 213It's slow but very precise.
 214
 215Table 1-2: Contents of the status files (as of 4.8)
 216..............................................................................
 217 Field                       Content
 218 Name                        filename of the executable
 219 Umask                       file mode creation mask
 220 State                       state (R is running, S is sleeping, D is sleeping
 221                             in an uninterruptible wait, Z is zombie,
 222                             T is traced or stopped)
 223 Tgid                        thread group ID
 224 Ngid                        NUMA group ID (0 if none)
 225 Pid                         process id
 226 PPid                        process id of the parent process
 227 TracerPid                   PID of process tracing this process (0 if not)
 228 Uid                         Real, effective, saved set, and  file system UIDs
 229 Gid                         Real, effective, saved set, and  file system GIDs
 230 FDSize                      number of file descriptor slots currently allocated
 231 Groups                      supplementary group list
 232 NStgid                      descendant namespace thread group ID hierarchy
 233 NSpid                       descendant namespace process ID hierarchy
 234 NSpgid                      descendant namespace process group ID hierarchy
 235 NSsid                       descendant namespace session ID hierarchy
 236 VmPeak                      peak virtual memory size
 237 VmSize                      total program size
 238 VmLck                       locked memory size
 239 VmPin                       pinned memory size
 240 VmHWM                       peak resident set size ("high water mark")
 241 VmRSS                       size of memory portions. It contains the three
 242                             following parts (VmRSS = RssAnon + RssFile + RssShmem)
 243 RssAnon                     size of resident anonymous memory
 244 RssFile                     size of resident file mappings
 245 RssShmem                    size of resident shmem memory (includes SysV shm,
 246                             mapping of tmpfs and shared anonymous mappings)
 247 VmData                      size of private data segments
 248 VmStk                       size of stack segments
 249 VmExe                       size of text segment
 250 VmLib                       size of shared library code
 251 VmPTE                       size of page table entries
 252 VmPMD                       size of second level page tables
 253 VmSwap                      amount of swap used by anonymous private data
 254                             (shmem swap usage is not included)
 255 HugetlbPages                size of hugetlb memory portions
 256 Threads                     number of threads
 257 SigQ                        number of signals queued/max. number for queue
 258 SigPnd                      bitmap of pending signals for the thread
 259 ShdPnd                      bitmap of shared pending signals for the process
 260 SigBlk                      bitmap of blocked signals
 261 SigIgn                      bitmap of ignored signals
 262 SigCgt                      bitmap of caught signals
 263 CapInh                      bitmap of inheritable capabilities
 264 CapPrm                      bitmap of permitted capabilities
 265 CapEff                      bitmap of effective capabilities
 266 CapBnd                      bitmap of capabilities bounding set
 267 NoNewPrivs                  no_new_privs, like prctl(PR_GET_NO_NEW_PRIV, ...)
 268 Seccomp                     seccomp mode, like prctl(PR_GET_SECCOMP, ...)
 269 Cpus_allowed                mask of CPUs on which this process may run
 270 Cpus_allowed_list           Same as previous, but in "list format"
 271 Mems_allowed                mask of memory nodes allowed to this process
 272 Mems_allowed_list           Same as previous, but in "list format"
 273 voluntary_ctxt_switches     number of voluntary context switches
 274 nonvoluntary_ctxt_switches  number of non voluntary context switches
 275..............................................................................
 276
 277Table 1-3: Contents of the statm files (as of 2.6.8-rc3)
 278..............................................................................
 279 Field    Content
 280 size     total program size (pages)            (same as VmSize in status)
 281 resident size of memory portions (pages)       (same as VmRSS in status)
 282 shared   number of pages that are shared       (i.e. backed by a file, same
 283                                                as RssFile+RssShmem in status)
 284 trs      number of pages that are 'code'       (not including libs; broken,
 285                                                        includes data segment)
 286 lrs      number of pages of library            (always 0 on 2.6)
 287 drs      number of pages of data/stack         (including libs; broken,
 288                                                        includes library text)
 289 dt       number of dirty pages                 (always 0 on 2.6)
 290..............................................................................
 291
 292
 293Table 1-4: Contents of the stat files (as of 2.6.30-rc7)
 294..............................................................................
 295 Field          Content
 296  pid           process id
 297  tcomm         filename of the executable
 298  state         state (R is running, S is sleeping, D is sleeping in an
 299                uninterruptible wait, Z is zombie, T is traced or stopped)
 300  ppid          process id of the parent process
 301  pgrp          pgrp of the process
 302  sid           session id
 303  tty_nr        tty the process uses
 304  tty_pgrp      pgrp of the tty
 305  flags         task flags
 306  min_flt       number of minor faults
 307  cmin_flt      number of minor faults with child's
 308  maj_flt       number of major faults
 309  cmaj_flt      number of major faults with child's
 310  utime         user mode jiffies
 311  stime         kernel mode jiffies
 312  cutime        user mode jiffies with child's
 313  cstime        kernel mode jiffies with child's
 314  priority      priority level
 315  nice          nice level
 316  num_threads   number of threads
 317  it_real_value (obsolete, always 0)
 318  start_time    time the process started after system boot
 319  vsize         virtual memory size
 320  rss           resident set memory size
 321  rsslim        current limit in bytes on the rss
 322  start_code    address above which program text can run
 323  end_code      address below which program text can run
 324  start_stack   address of the start of the main process stack
 325  esp           current value of ESP
 326  eip           current value of EIP
 327  pending       bitmap of pending signals
 328  blocked       bitmap of blocked signals
 329  sigign        bitmap of ignored signals
 330  sigcatch      bitmap of caught signals
 331  0             (place holder, used to be the wchan address, use /proc/PID/wchan instead)
 332  0             (place holder)
 333  0             (place holder)
 334  exit_signal   signal to send to parent thread on exit
 335  task_cpu      which CPU the task is scheduled on
 336  rt_priority   realtime priority
 337  policy        scheduling policy (man sched_setscheduler)
 338  blkio_ticks   time spent waiting for block IO
 339  gtime         guest time of the task in jiffies
 340  cgtime        guest time of the task children in jiffies
 341  start_data    address above which program data+bss is placed
 342  end_data      address below which program data+bss is placed
 343  start_brk     address above which program heap can be expanded with brk()
 344  arg_start     address above which program command line is placed
 345  arg_end       address below which program command line is placed
 346  env_start     address above which program environment is placed
 347  env_end       address below which program environment is placed
 348  exit_code     the thread's exit_code in the form reported by the waitpid system call
 349..............................................................................
 350
 351The /proc/PID/maps file containing the currently mapped memory regions and
 352their access permissions.
 353
 354The format is:
 355
 356address           perms offset  dev   inode      pathname
 357
 35808048000-08049000 r-xp 00000000 03:00 8312       /opt/test
 35908049000-0804a000 rw-p 00001000 03:00 8312       /opt/test
 3600804a000-0806b000 rw-p 00000000 00:00 0          [heap]
 361a7cb1000-a7cb2000 ---p 00000000 00:00 0
 362a7cb2000-a7eb2000 rw-p 00000000 00:00 0
 363a7eb2000-a7eb3000 ---p 00000000 00:00 0
 364a7eb3000-a7ed5000 rw-p 00000000 00:00 0
 365a7ed5000-a8008000 r-xp 00000000 03:00 4222       /lib/libc.so.6
 366a8008000-a800a000 r--p 00133000 03:00 4222       /lib/libc.so.6
 367a800a000-a800b000 rw-p 00135000 03:00 4222       /lib/libc.so.6
 368a800b000-a800e000 rw-p 00000000 00:00 0
 369a800e000-a8022000 r-xp 00000000 03:00 14462      /lib/libpthread.so.0
 370a8022000-a8023000 r--p 00013000 03:00 14462      /lib/libpthread.so.0
 371a8023000-a8024000 rw-p 00014000 03:00 14462      /lib/libpthread.so.0
 372a8024000-a8027000 rw-p 00000000 00:00 0
 373a8027000-a8043000 r-xp 00000000 03:00 8317       /lib/ld-linux.so.2
 374a8043000-a8044000 r--p 0001b000 03:00 8317       /lib/ld-linux.so.2
 375a8044000-a8045000 rw-p 0001c000 03:00 8317       /lib/ld-linux.so.2
 376aff35000-aff4a000 rw-p 00000000 00:00 0          [stack]
 377ffffe000-fffff000 r-xp 00000000 00:00 0          [vdso]
 378
 379where "address" is the address space in the process that it occupies, "perms"
 380is a set of permissions:
 381
 382 r = read
 383 w = write
 384 x = execute
 385 s = shared
 386 p = private (copy on write)
 387
 388"offset" is the offset into the mapping, "dev" is the device (major:minor), and
 389"inode" is the inode  on that device.  0 indicates that  no inode is associated
 390with the memory region, as the case would be with BSS (uninitialized data).
 391The "pathname" shows the name associated file for this mapping.  If the mapping
 392is not associated with a file:
 393
 394 [heap]                   = the heap of the program
 395 [stack]                  = the stack of the main process
 396 [vdso]                   = the "virtual dynamic shared object",
 397                            the kernel system call handler
 398
 399 or if empty, the mapping is anonymous.
 400
 401The /proc/PID/smaps is an extension based on maps, showing the memory
 402consumption for each of the process's mappings. For each of mappings there
 403is a series of lines such as the following:
 404
 40508048000-080bc000 r-xp 00000000 03:02 13130      /bin/bash
 406Size:               1084 kB
 407Rss:                 892 kB
 408Pss:                 374 kB
 409Shared_Clean:        892 kB
 410Shared_Dirty:          0 kB
 411Private_Clean:         0 kB
 412Private_Dirty:         0 kB
 413Referenced:          892 kB
 414Anonymous:             0 kB
 415AnonHugePages:         0 kB
 416ShmemPmdMapped:        0 kB
 417Shared_Hugetlb:        0 kB
 418Private_Hugetlb:       0 kB
 419Swap:                  0 kB
 420SwapPss:               0 kB
 421KernelPageSize:        4 kB
 422MMUPageSize:           4 kB
 423Locked:                0 kB
 424VmFlags: rd ex mr mw me dw
 425
 426the first of these lines shows the same information as is displayed for the
 427mapping in /proc/PID/maps.  The remaining lines show the size of the mapping
 428(size), the amount of the mapping that is currently resident in RAM (RSS), the
 429process' proportional share of this mapping (PSS), the number of clean and
 430dirty private pages in the mapping.
 431
 432The "proportional set size" (PSS) of a process is the count of pages it has
 433in memory, where each page is divided by the number of processes sharing it.
 434So if a process has 1000 pages all to itself, and 1000 shared with one other
 435process, its PSS will be 1500.
 436Note that even a page which is part of a MAP_SHARED mapping, but has only
 437a single pte mapped, i.e.  is currently used by only one process, is accounted
 438as private and not as shared.
 439"Referenced" indicates the amount of memory currently marked as referenced or
 440accessed.
 441"Anonymous" shows the amount of memory that does not belong to any file.  Even
 442a mapping associated with a file may contain anonymous pages: when MAP_PRIVATE
 443and a page is modified, the file page is replaced by a private anonymous copy.
 444"AnonHugePages" shows the ammount of memory backed by transparent hugepage.
 445"ShmemPmdMapped" shows the ammount of shared (shmem/tmpfs) memory backed by
 446huge pages.
 447"Shared_Hugetlb" and "Private_Hugetlb" show the ammounts of memory backed by
 448hugetlbfs page which is *not* counted in "RSS" or "PSS" field for historical
 449reasons. And these are not included in {Shared,Private}_{Clean,Dirty} field.
 450"Swap" shows how much would-be-anonymous memory is also used, but out on swap.
 451For shmem mappings, "Swap" includes also the size of the mapped (and not
 452replaced by copy-on-write) part of the underlying shmem object out on swap.
 453"SwapPss" shows proportional swap share of this mapping. Unlike "Swap", this
 454does not take into account swapped out page of underlying shmem objects.
 455"Locked" indicates whether the mapping is locked in memory or not.
 456
 457"VmFlags" field deserves a separate description. This member represents the kernel
 458flags associated with the particular virtual memory area in two letter encoded
 459manner. The codes are the following:
 460    rd  - readable
 461    wr  - writeable
 462    ex  - executable
 463    sh  - shared
 464    mr  - may read
 465    mw  - may write
 466    me  - may execute
 467    ms  - may share
 468    gd  - stack segment growns down
 469    pf  - pure PFN range
 470    dw  - disabled write to the mapped file
 471    lo  - pages are locked in memory
 472    io  - memory mapped I/O area
 473    sr  - sequential read advise provided
 474    rr  - random read advise provided
 475    dc  - do not copy area on fork
 476    de  - do not expand area on remapping
 477    ac  - area is accountable
 478    nr  - swap space is not reserved for the area
 479    ht  - area uses huge tlb pages
 480    ar  - architecture specific flag
 481    dd  - do not include area into core dump
 482    sd  - soft-dirty flag
 483    mm  - mixed map area
 484    hg  - huge page advise flag
 485    nh  - no-huge page advise flag
 486    mg  - mergable advise flag
 487
 488Note that there is no guarantee that every flag and associated mnemonic will
 489be present in all further kernel releases. Things get changed, the flags may
 490be vanished or the reverse -- new added.
 491
 492This file is only present if the CONFIG_MMU kernel configuration option is
 493enabled.
 494
 495Note: reading /proc/PID/maps or /proc/PID/smaps is inherently racy (consistent
 496output can be achieved only in the single read call).
 497This typically manifests when doing partial reads of these files while the
 498memory map is being modified.  Despite the races, we do provide the following
 499guarantees:
 500
 5011) The mapped addresses never go backwards, which implies no two
 502   regions will ever overlap.
 5032) If there is something at a given vaddr during the entirety of the
 504   life of the smaps/maps walk, there will be some output for it.
 505
 506
 507The /proc/PID/clear_refs is used to reset the PG_Referenced and ACCESSED/YOUNG
 508bits on both physical and virtual pages associated with a process, and the
 509soft-dirty bit on pte (see Documentation/vm/soft-dirty.txt for details).
 510To clear the bits for all the pages associated with the process
 511    > echo 1 > /proc/PID/clear_refs
 512
 513To clear the bits for the anonymous pages associated with the process
 514    > echo 2 > /proc/PID/clear_refs
 515
 516To clear the bits for the file mapped pages associated with the process
 517    > echo 3 > /proc/PID/clear_refs
 518
 519To clear the soft-dirty bit
 520    > echo 4 > /proc/PID/clear_refs
 521
 522To reset the peak resident set size ("high water mark") to the process's
 523current value:
 524    > echo 5 > /proc/PID/clear_refs
 525
 526Any other value written to /proc/PID/clear_refs will have no effect.
 527
 528The /proc/pid/pagemap gives the PFN, which can be used to find the pageflags
 529using /proc/kpageflags and number of times a page is mapped using
 530/proc/kpagecount. For detailed explanation, see Documentation/vm/pagemap.txt.
 531
 532The /proc/pid/numa_maps is an extension based on maps, showing the memory
 533locality and binding policy, as well as the memory usage (in pages) of
 534each mapping. The output follows a general format where mapping details get
 535summarized separated by blank spaces, one mapping per each file line:
 536
 537address   policy    mapping details
 538
 53900400000 default file=/usr/local/bin/app mapped=1 active=0 N3=1 kernelpagesize_kB=4
 54000600000 default file=/usr/local/bin/app anon=1 dirty=1 N3=1 kernelpagesize_kB=4
 5413206000000 default file=/lib64/ld-2.12.so mapped=26 mapmax=6 N0=24 N3=2 kernelpagesize_kB=4
 542320621f000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
 5433206220000 default file=/lib64/ld-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
 5443206221000 default anon=1 dirty=1 N3=1 kernelpagesize_kB=4
 5453206800000 default file=/lib64/libc-2.12.so mapped=59 mapmax=21 active=55 N0=41 N3=18 kernelpagesize_kB=4
 546320698b000 default file=/lib64/libc-2.12.so
 5473206b8a000 default file=/lib64/libc-2.12.so anon=2 dirty=2 N3=2 kernelpagesize_kB=4
 5483206b8e000 default file=/lib64/libc-2.12.so anon=1 dirty=1 N3=1 kernelpagesize_kB=4
 5493206b8f000 default anon=3 dirty=3 active=1 N3=3 kernelpagesize_kB=4
 5507f4dc10a2000 default anon=3 dirty=3 N3=3 kernelpagesize_kB=4
 5517f4dc10b4000 default anon=2 dirty=2 active=1 N3=2 kernelpagesize_kB=4
 5527f4dc1200000 default file=/anon_hugepage\040(deleted) huge anon=1 dirty=1 N3=1 kernelpagesize_kB=2048
 5537fff335f0000 default stack anon=3 dirty=3 N3=3 kernelpagesize_kB=4
 5547fff3369d000 default mapped=1 mapmax=35 active=0 N3=1 kernelpagesize_kB=4
 555
 556Where:
 557"address" is the starting address for the mapping;
 558"policy" reports the NUMA memory policy set for the mapping (see vm/numa_memory_policy.txt);
 559"mapping details" summarizes mapping data such as mapping type, page usage counters,
 560node locality page counters (N0 == node0, N1 == node1, ...) and the kernel page
 561size, in KB, that is backing the mapping up.
 562
 5631.2 Kernel data
 564---------------
 565
 566Similar to  the  process entries, the kernel data files give information about
 567the running kernel. The files used to obtain this information are contained in
 568/proc and  are  listed  in Table 1-5. Not all of these will be present in your
 569system. It  depends  on the kernel configuration and the loaded modules, which
 570files are there, and which are missing.
 571
 572Table 1-5: Kernel info in /proc
 573..............................................................................
 574 File        Content                                           
 575 apm         Advanced power management info                    
 576 buddyinfo   Kernel memory allocator information (see text)     (2.5)
 577 bus         Directory containing bus specific information     
 578 cmdline     Kernel command line                               
 579 cpuinfo     Info about the CPU                                
 580 devices     Available devices (block and character)           
 581 dma         Used DMS channels                                 
 582 filesystems Supported filesystems                             
 583 driver      Various drivers grouped here, currently rtc (2.4)
 584 execdomains Execdomains, related to security                   (2.4)
 585 fb          Frame Buffer devices                               (2.4)
 586 fs          File system parameters, currently nfs/exports      (2.4)
 587 ide         Directory containing info about the IDE subsystem 
 588 interrupts  Interrupt usage                                   
 589 iomem       Memory map                                         (2.4)
 590 ioports     I/O port usage                                    
 591 irq         Masks for irq to cpu affinity                      (2.4)(smp?)
 592 isapnp      ISA PnP (Plug&Play) Info                           (2.4)
 593 kcore       Kernel core image (can be ELF or A.OUT(deprecated in 2.4))   
 594 kmsg        Kernel messages                                   
 595 ksyms       Kernel symbol table                               
 596 loadavg     Load average of last 1, 5 & 15 minutes                
 597 locks       Kernel locks                                      
 598 meminfo     Memory info                                       
 599 misc        Miscellaneous                                     
 600 modules     List of loaded modules                            
 601 mounts      Mounted filesystems                               
 602 net         Networking info (see text)                        
 603 pagetypeinfo Additional page allocator information (see text)  (2.5)
 604 partitions  Table of partitions known to the system           
 605 pci         Deprecated info of PCI bus (new way -> /proc/bus/pci/,
 606             decoupled by lspci                                 (2.4)
 607 rtc         Real time clock                                   
 608 scsi        SCSI info (see text)                              
 609 slabinfo    Slab pool info                                    
 610 softirqs    softirq usage
 611 stat        Overall statistics                                
 612 swaps       Swap space utilization                            
 613 sys         See chapter 2                                     
 614 sysvipc     Info of SysVIPC Resources (msg, sem, shm)          (2.4)
 615 tty         Info of tty drivers
 616 uptime      Wall clock since boot, combined idle time of all cpus
 617 version     Kernel version                                    
 618 video       bttv info of video resources                       (2.4)
 619 vmallocinfo Show vmalloced areas
 620..............................................................................
 621
 622You can,  for  example,  check  which interrupts are currently in use and what
 623they are used for by looking in the file /proc/interrupts:
 624
 625  > cat /proc/interrupts 
 626             CPU0        
 627    0:    8728810          XT-PIC  timer 
 628    1:        895          XT-PIC  keyboard 
 629    2:          0          XT-PIC  cascade 
 630    3:     531695          XT-PIC  aha152x 
 631    4:    2014133          XT-PIC  serial 
 632    5:      44401          XT-PIC  pcnet_cs 
 633    8:          2          XT-PIC  rtc 
 634   11:          8          XT-PIC  i82365 
 635   12:     182918          XT-PIC  PS/2 Mouse 
 636   13:          1          XT-PIC  fpu 
 637   14:    1232265          XT-PIC  ide0 
 638   15:          7          XT-PIC  ide1 
 639  NMI:          0 
 640
 641In 2.4.* a couple of lines where added to this file LOC & ERR (this time is the
 642output of a SMP machine):
 643
 644  > cat /proc/interrupts 
 645
 646             CPU0       CPU1       
 647    0:    1243498    1214548    IO-APIC-edge  timer
 648    1:       8949       8958    IO-APIC-edge  keyboard
 649    2:          0          0          XT-PIC  cascade
 650    5:      11286      10161    IO-APIC-edge  soundblaster
 651    8:          1          0    IO-APIC-edge  rtc
 652    9:      27422      27407    IO-APIC-edge  3c503
 653   12:     113645     113873    IO-APIC-edge  PS/2 Mouse
 654   13:          0          0          XT-PIC  fpu
 655   14:      22491      24012    IO-APIC-edge  ide0
 656   15:       2183       2415    IO-APIC-edge  ide1
 657   17:      30564      30414   IO-APIC-level  eth0
 658   18:        177        164   IO-APIC-level  bttv
 659  NMI:    2457961    2457959 
 660  LOC:    2457882    2457881 
 661  ERR:       2155
 662
 663NMI is incremented in this case because every timer interrupt generates a NMI
 664(Non Maskable Interrupt) which is used by the NMI Watchdog to detect lockups.
 665
 666LOC is the local interrupt counter of the internal APIC of every CPU.
 667
 668ERR is incremented in the case of errors in the IO-APIC bus (the bus that
 669connects the CPUs in a SMP system. This means that an error has been detected,
 670the IO-APIC automatically retry the transmission, so it should not be a big
 671problem, but you should read the SMP-FAQ.
 672
 673In 2.6.2* /proc/interrupts was expanded again.  This time the goal was for
 674/proc/interrupts to display every IRQ vector in use by the system, not
 675just those considered 'most important'.  The new vectors are:
 676
 677  THR -- interrupt raised when a machine check threshold counter
 678  (typically counting ECC corrected errors of memory or cache) exceeds
 679  a configurable threshold.  Only available on some systems.
 680
 681  TRM -- a thermal event interrupt occurs when a temperature threshold
 682  has been exceeded for the CPU.  This interrupt may also be generated
 683  when the temperature drops back to normal.
 684
 685  SPU -- a spurious interrupt is some interrupt that was raised then lowered
 686  by some IO device before it could be fully processed by the APIC.  Hence
 687  the APIC sees the interrupt but does not know what device it came from.
 688  For this case the APIC will generate the interrupt with a IRQ vector
 689  of 0xff. This might also be generated by chipset bugs.
 690
 691  RES, CAL, TLB -- rescheduling, call and TLB flush interrupts are
 692  sent from one CPU to another per the needs of the OS.  Typically,
 693  their statistics are used by kernel developers and interested users to
 694  determine the occurrence of interrupts of the given type.
 695
 696The above IRQ vectors are displayed only when relevant.  For example,
 697the threshold vector does not exist on x86_64 platforms.  Others are
 698suppressed when the system is a uniprocessor.  As of this writing, only
 699i386 and x86_64 platforms support the new IRQ vector displays.
 700
 701Of some interest is the introduction of the /proc/irq directory to 2.4.
 702It could be used to set IRQ to CPU affinity, this means that you can "hook" an
 703IRQ to only one CPU, or to exclude a CPU of handling IRQs. The contents of the
 704irq subdir is one subdir for each IRQ, and two files; default_smp_affinity and
 705prof_cpu_mask.
 706
 707For example 
 708  > ls /proc/irq/
 709  0  10  12  14  16  18  2  4  6  8  prof_cpu_mask
 710  1  11  13  15  17  19  3  5  7  9  default_smp_affinity
 711  > ls /proc/irq/0/
 712  smp_affinity
 713
 714smp_affinity is a bitmask, in which you can specify which CPUs can handle the
 715IRQ, you can set it by doing:
 716
 717  > echo 1 > /proc/irq/10/smp_affinity
 718
 719This means that only the first CPU will handle the IRQ, but you can also echo
 7205 which means that only the first and third CPU can handle the IRQ.
 721
 722The contents of each smp_affinity file is the same by default:
 723
 724  > cat /proc/irq/0/smp_affinity
 725  ffffffff
 726
 727There is an alternate interface, smp_affinity_list which allows specifying
 728a cpu range instead of a bitmask:
 729
 730  > cat /proc/irq/0/smp_affinity_list
 731  1024-1031
 732
 733The default_smp_affinity mask applies to all non-active IRQs, which are the
 734IRQs which have not yet been allocated/activated, and hence which lack a
 735/proc/irq/[0-9]* directory.
 736
 737The node file on an SMP system shows the node to which the device using the IRQ
 738reports itself as being attached. This hardware locality information does not
 739include information about any possible driver locality preference.
 740
 741prof_cpu_mask specifies which CPUs are to be profiled by the system wide
 742profiler. Default value is ffffffff (all cpus if there are only 32 of them).
 743
 744The way IRQs are routed is handled by the IO-APIC, and it's Round Robin
 745between all the CPUs which are allowed to handle it. As usual the kernel has
 746more info than you and does a better job than you, so the defaults are the
 747best choice for almost everyone.  [Note this applies only to those IO-APIC's
 748that support "Round Robin" interrupt distribution.]
 749
 750There are  three  more  important subdirectories in /proc: net, scsi, and sys.
 751The general  rule  is  that  the  contents,  or  even  the  existence of these
 752directories, depend  on your kernel configuration. If SCSI is not enabled, the
 753directory scsi  may  not  exist. The same is true with the net, which is there
 754only when networking support is present in the running kernel.
 755
 756The slabinfo  file  gives  information  about  memory usage at the slab level.
 757Linux uses  slab  pools for memory management above page level in version 2.2.
 758Commonly used  objects  have  their  own  slab  pool (such as network buffers,
 759directory cache, and so on).
 760
 761..............................................................................
 762
 763> cat /proc/buddyinfo
 764
 765Node 0, zone      DMA      0      4      5      4      4      3 ...
 766Node 0, zone   Normal      1      0      0      1    101      8 ...
 767Node 0, zone  HighMem      2      0      0      1      1      0 ...
 768
 769External fragmentation is a problem under some workloads, and buddyinfo is a
 770useful tool for helping diagnose these problems.  Buddyinfo will give you a 
 771clue as to how big an area you can safely allocate, or why a previous
 772allocation failed.
 773
 774Each column represents the number of pages of a certain order which are 
 775available.  In this case, there are 0 chunks of 2^0*PAGE_SIZE available in 
 776ZONE_DMA, 4 chunks of 2^1*PAGE_SIZE in ZONE_DMA, 101 chunks of 2^4*PAGE_SIZE 
 777available in ZONE_NORMAL, etc... 
 778
 779More information relevant to external fragmentation can be found in
 780pagetypeinfo.
 781
 782> cat /proc/pagetypeinfo
 783Page block order: 9
 784Pages per block:  512
 785
 786Free pages count per migrate type at order       0      1      2      3      4      5      6      7      8      9     10
 787Node    0, zone      DMA, type    Unmovable      0      0      0      1      1      1      1      1      1      1      0
 788Node    0, zone      DMA, type  Reclaimable      0      0      0      0      0      0      0      0      0      0      0
 789Node    0, zone      DMA, type      Movable      1      1      2      1      2      1      1      0      1      0      2
 790Node    0, zone      DMA, type      Reserve      0      0      0      0      0      0      0      0      0      1      0
 791Node    0, zone      DMA, type      Isolate      0      0      0      0      0      0      0      0      0      0      0
 792Node    0, zone    DMA32, type    Unmovable    103     54     77      1      1      1     11      8      7      1      9
 793Node    0, zone    DMA32, type  Reclaimable      0      0      2      1      0      0      0      0      1      0      0
 794Node    0, zone    DMA32, type      Movable    169    152    113     91     77     54     39     13      6      1    452
 795Node    0, zone    DMA32, type      Reserve      1      2      2      2      2      0      1      1      1      1      0
 796Node    0, zone    DMA32, type      Isolate      0      0      0      0      0      0      0      0      0      0      0
 797
 798Number of blocks type     Unmovable  Reclaimable      Movable      Reserve      Isolate
 799Node 0, zone      DMA            2            0            5            1            0
 800Node 0, zone    DMA32           41            6          967            2            0
 801
 802Fragmentation avoidance in the kernel works by grouping pages of different
 803migrate types into the same contiguous regions of memory called page blocks.
 804A page block is typically the size of the default hugepage size e.g. 2MB on
 805X86-64. By keeping pages grouped based on their ability to move, the kernel
 806can reclaim pages within a page block to satisfy a high-order allocation.
 807
 808The pagetypinfo begins with information on the size of a page block. It
 809then gives the same type of information as buddyinfo except broken down
 810by migrate-type and finishes with details on how many page blocks of each
 811type exist.
 812
 813If min_free_kbytes has been tuned correctly (recommendations made by hugeadm
 814from libhugetlbfs https://github.com/libhugetlbfs/libhugetlbfs/), one can
 815make an estimate of the likely number of huge pages that can be allocated
 816at a given point in time. All the "Movable" blocks should be allocatable
 817unless memory has been mlock()'d. Some of the Reclaimable blocks should
 818also be allocatable although a lot of filesystem metadata may have to be
 819reclaimed to achieve this.
 820
 821..............................................................................
 822
 823meminfo:
 824
 825Provides information about distribution and utilization of memory.  This
 826varies by architecture and compile options.  The following is from a
 82716GB PIII, which has highmem enabled.  You may not have all of these fields.
 828
 829> cat /proc/meminfo
 830
 831MemTotal:     16344972 kB
 832MemFree:      13634064 kB
 833MemAvailable: 14836172 kB
 834Buffers:          3656 kB
 835Cached:        1195708 kB
 836SwapCached:          0 kB
 837Active:         891636 kB
 838Inactive:      1077224 kB
 839HighTotal:    15597528 kB
 840HighFree:     13629632 kB
 841LowTotal:       747444 kB
 842LowFree:          4432 kB
 843SwapTotal:           0 kB
 844SwapFree:            0 kB
 845Dirty:             968 kB
 846Writeback:           0 kB
 847AnonPages:      861800 kB
 848Mapped:         280372 kB
 849Shmem:             644 kB
 850Slab:           284364 kB
 851SReclaimable:   159856 kB
 852SUnreclaim:     124508 kB
 853PageTables:      24448 kB
 854NFS_Unstable:        0 kB
 855Bounce:              0 kB
 856WritebackTmp:        0 kB
 857CommitLimit:   7669796 kB
 858Committed_AS:   100056 kB
 859VmallocTotal:   112216 kB
 860VmallocUsed:       428 kB
 861VmallocChunk:   111088 kB
 862AnonHugePages:   49152 kB
 863ShmemHugePages:      0 kB
 864ShmemPmdMapped:      0 kB
 865
 866
 867    MemTotal: Total usable ram (i.e. physical ram minus a few reserved
 868              bits and the kernel binary code)
 869     MemFree: The sum of LowFree+HighFree
 870MemAvailable: An estimate of how much memory is available for starting new
 871              applications, without swapping. Calculated from MemFree,
 872              SReclaimable, the size of the file LRU lists, and the low
 873              watermarks in each zone.
 874              The estimate takes into account that the system needs some
 875              page cache to function well, and that not all reclaimable
 876              slab will be reclaimable, due to items being in use. The
 877              impact of those factors will vary from system to system.
 878     Buffers: Relatively temporary storage for raw disk blocks
 879              shouldn't get tremendously large (20MB or so)
 880      Cached: in-memory cache for files read from the disk (the
 881              pagecache).  Doesn't include SwapCached
 882  SwapCached: Memory that once was swapped out, is swapped back in but
 883              still also is in the swapfile (if memory is needed it
 884              doesn't need to be swapped out AGAIN because it is already
 885              in the swapfile. This saves I/O)
 886      Active: Memory that has been used more recently and usually not
 887              reclaimed unless absolutely necessary.
 888    Inactive: Memory which has been less recently used.  It is more
 889              eligible to be reclaimed for other purposes
 890   HighTotal:
 891    HighFree: Highmem is all memory above ~860MB of physical memory
 892              Highmem areas are for use by userspace programs, or
 893              for the pagecache.  The kernel must use tricks to access
 894              this memory, making it slower to access than lowmem.
 895    LowTotal:
 896     LowFree: Lowmem is memory which can be used for everything that
 897              highmem can be used for, but it is also available for the
 898              kernel's use for its own data structures.  Among many
 899              other things, it is where everything from the Slab is
 900              allocated.  Bad things happen when you're out of lowmem.
 901   SwapTotal: total amount of swap space available
 902    SwapFree: Memory which has been evicted from RAM, and is temporarily
 903              on the disk
 904       Dirty: Memory which is waiting to get written back to the disk
 905   Writeback: Memory which is actively being written back to the disk
 906   AnonPages: Non-file backed pages mapped into userspace page tables
 907AnonHugePages: Non-file backed huge pages mapped into userspace page tables
 908      Mapped: files which have been mmaped, such as libraries
 909       Shmem: Total memory used by shared memory (shmem) and tmpfs
 910ShmemHugePages: Memory used by shared memory (shmem) and tmpfs allocated
 911              with huge pages
 912ShmemPmdMapped: Shared memory mapped into userspace with huge pages
 913        Slab: in-kernel data structures cache
 914SReclaimable: Part of Slab, that might be reclaimed, such as caches
 915  SUnreclaim: Part of Slab, that cannot be reclaimed on memory pressure
 916  PageTables: amount of memory dedicated to the lowest level of page
 917              tables.
 918NFS_Unstable: NFS pages sent to the server, but not yet committed to stable
 919              storage
 920      Bounce: Memory used for block device "bounce buffers"
 921WritebackTmp: Memory used by FUSE for temporary writeback buffers
 922 CommitLimit: Based on the overcommit ratio ('vm.overcommit_ratio'),
 923              this is the total amount of  memory currently available to
 924              be allocated on the system. This limit is only adhered to
 925              if strict overcommit accounting is enabled (mode 2 in
 926              'vm.overcommit_memory').
 927              The CommitLimit is calculated with the following formula:
 928              CommitLimit = ([total RAM pages] - [total huge TLB pages]) *
 929                             overcommit_ratio / 100 + [total swap pages]
 930              For example, on a system with 1G of physical RAM and 7G
 931              of swap with a `vm.overcommit_ratio` of 30 it would
 932              yield a CommitLimit of 7.3G.
 933              For more details, see the memory overcommit documentation
 934              in vm/overcommit-accounting.
 935Committed_AS: The amount of memory presently allocated on the system.
 936              The committed memory is a sum of all of the memory which
 937              has been allocated by processes, even if it has not been
 938              "used" by them as of yet. A process which malloc()'s 1G
 939              of memory, but only touches 300M of it will show up as
 940              using 1G. This 1G is memory which has been "committed" to
 941              by the VM and can be used at any time by the allocating
 942              application. With strict overcommit enabled on the system
 943              (mode 2 in 'vm.overcommit_memory'),allocations which would
 944              exceed the CommitLimit (detailed above) will not be permitted.
 945              This is useful if one needs to guarantee that processes will
 946              not fail due to lack of memory once that memory has been
 947              successfully allocated.
 948VmallocTotal: total size of vmalloc memory area
 949 VmallocUsed: amount of vmalloc area which is used
 950VmallocChunk: largest contiguous block of vmalloc area which is free
 951
 952..............................................................................
 953
 954vmallocinfo:
 955
 956Provides information about vmalloced/vmaped areas. One line per area,
 957containing the virtual address range of the area, size in bytes,
 958caller information of the creator, and optional information depending
 959on the kind of area :
 960
 961 pages=nr    number of pages
 962 phys=addr   if a physical address was specified
 963 ioremap     I/O mapping (ioremap() and friends)
 964 vmalloc     vmalloc() area
 965 vmap        vmap()ed pages
 966 user        VM_USERMAP area
 967 vpages      buffer for pages pointers was vmalloced (huge area)
 968 N<node>=nr  (Only on NUMA kernels)
 969             Number of pages allocated on memory node <node>
 970
 971> cat /proc/vmallocinfo
 9720xffffc20000000000-0xffffc20000201000 2101248 alloc_large_system_hash+0x204 ...
 973  /0x2c0 pages=512 vmalloc N0=128 N1=128 N2=128 N3=128
 9740xffffc20000201000-0xffffc20000302000 1052672 alloc_large_system_hash+0x204 ...
 975  /0x2c0 pages=256 vmalloc N0=64 N1=64 N2=64 N3=64
 9760xffffc20000302000-0xffffc20000304000    8192 acpi_tb_verify_table+0x21/0x4f...
 977  phys=7fee8000 ioremap
 9780xffffc20000304000-0xffffc20000307000   12288 acpi_tb_verify_table+0x21/0x4f...
 979  phys=7fee7000 ioremap
 9800xffffc2000031d000-0xffffc2000031f000    8192 init_vdso_vars+0x112/0x210
 9810xffffc2000031f000-0xffffc2000032b000   49152 cramfs_uncompress_init+0x2e ...
 982  /0x80 pages=11 vmalloc N0=3 N1=3 N2=2 N3=3
 9830xffffc2000033a000-0xffffc2000033d000   12288 sys_swapon+0x640/0xac0      ...
 984  pages=2 vmalloc N1=2
 9850xffffc20000347000-0xffffc2000034c000   20480 xt_alloc_table_info+0xfe ...
 986  /0x130 [x_tables] pages=4 vmalloc N0=4
 9870xffffffffa0000000-0xffffffffa000f000   61440 sys_init_module+0xc27/0x1d00 ...
 988   pages=14 vmalloc N2=14
 9890xffffffffa000f000-0xffffffffa0014000   20480 sys_init_module+0xc27/0x1d00 ...
 990   pages=4 vmalloc N1=4
 9910xffffffffa0014000-0xffffffffa0017000   12288 sys_init_module+0xc27/0x1d00 ...
 992   pages=2 vmalloc N1=2
 9930xffffffffa0017000-0xffffffffa0022000   45056 sys_init_module+0xc27/0x1d00 ...
 994   pages=10 vmalloc N0=10
 995
 996..............................................................................
 997
 998softirqs:
 999
1000Provides counts of softirq handlers serviced since boot time, for each cpu.
1001
1002> cat /proc/softirqs
1003                CPU0       CPU1       CPU2       CPU3
1004      HI:          0          0          0          0
1005   TIMER:      27166      27120      27097      27034
1006  NET_TX:          0          0          0         17
1007  NET_RX:         42          0          0         39
1008   BLOCK:          0          0        107       1121
1009 TASKLET:          0          0          0        290
1010   SCHED:      27035      26983      26971      26746
1011 HRTIMER:          0          0          0          0
1012     RCU:       1678       1769       2178       2250
1013
1014
10151.3 IDE devices in /proc/ide
1016----------------------------
1017
1018The subdirectory /proc/ide contains information about all IDE devices of which
1019the kernel  is  aware.  There is one subdirectory for each IDE controller, the
1020file drivers  and a link for each IDE device, pointing to the device directory
1021in the controller specific subtree.
1022
1023The file  drivers  contains general information about the drivers used for the
1024IDE devices:
1025
1026  > cat /proc/ide/drivers
1027  ide-cdrom version 4.53
1028  ide-disk version 1.08
1029
1030More detailed  information  can  be  found  in  the  controller  specific
1031subdirectories. These  are  named  ide0,  ide1  and  so  on.  Each  of  these
1032directories contains the files shown in table 1-6.
1033
1034
1035Table 1-6: IDE controller info in  /proc/ide/ide?
1036..............................................................................
1037 File    Content                                 
1038 channel IDE channel (0 or 1)                    
1039 config  Configuration (only for PCI/IDE bridge) 
1040 mate    Mate name                               
1041 model   Type/Chipset of IDE controller          
1042..............................................................................
1043
1044Each device  connected  to  a  controller  has  a separate subdirectory in the
1045controllers directory.  The  files  listed in table 1-7 are contained in these
1046directories.
1047
1048
1049Table 1-7: IDE device information
1050..............................................................................
1051 File             Content                                    
1052 cache            The cache                                  
1053 capacity         Capacity of the medium (in 512Byte blocks) 
1054 driver           driver and version                         
1055 geometry         physical and logical geometry              
1056 identify         device identify block                      
1057 media            media type                                 
1058 model            device identifier                          
1059 settings         device setup                               
1060 smart_thresholds IDE disk management thresholds             
1061 smart_values     IDE disk management values                 
1062..............................................................................
1063
1064The most  interesting  file is settings. This file contains a nice overview of
1065the drive parameters:
1066
1067  # cat /proc/ide/ide0/hda/settings 
1068  name                    value           min             max             mode 
1069  ----                    -----           ---             ---             ---- 
1070  bios_cyl                526             0               65535           rw 
1071  bios_head               255             0               255             rw 
1072  bios_sect               63              0               63              rw 
1073  breada_readahead        4               0               127             rw 
1074  bswap                   0               0               1               r 
1075  file_readahead          72              0               2097151         rw 
1076  io_32bit                0               0               3               rw 
1077  keepsettings            0               0               1               rw 
1078  max_kb_per_request      122             1               127             rw 
1079  multcount               0               0               8               rw 
1080  nice1                   1               0               1               rw 
1081  nowerr                  0               0               1               rw 
1082  pio_mode                write-only      0               255             w 
1083  slow                    0               0               1               rw 
1084  unmaskirq               0               0               1               rw 
1085  using_dma               0               0               1               rw 
1086
1087
10881.4 Networking info in /proc/net
1089--------------------------------
1090
1091The subdirectory  /proc/net  follows  the  usual  pattern. Table 1-8 shows the
1092additional values  you  get  for  IP  version 6 if you configure the kernel to
1093support this. Table 1-9 lists the files and their meaning.
1094
1095
1096Table 1-8: IPv6 info in /proc/net
1097..............................................................................
1098 File       Content                                               
1099 udp6       UDP sockets (IPv6)                                    
1100 tcp6       TCP sockets (IPv6)                                    
1101 raw6       Raw device statistics (IPv6)                          
1102 igmp6      IP multicast addresses, which this host joined (IPv6) 
1103 if_inet6   List of IPv6 interface addresses                      
1104 ipv6_route Kernel routing table for IPv6                         
1105 rt6_stats  Global IPv6 routing tables statistics                 
1106 sockstat6  Socket statistics (IPv6)                              
1107 snmp6      Snmp data (IPv6)                                      
1108..............................................................................
1109
1110
1111Table 1-9: Network info in /proc/net
1112..............................................................................
1113 File          Content                                                         
1114 arp           Kernel  ARP table                                               
1115 dev           network devices with statistics                                 
1116 dev_mcast     the Layer2 multicast groups a device is listening too
1117               (interface index, label, number of references, number of bound
1118               addresses). 
1119 dev_stat      network device status                                           
1120 ip_fwchains   Firewall chain linkage                                          
1121 ip_fwnames    Firewall chain names                                            
1122 ip_masq       Directory containing the masquerading tables                    
1123 ip_masquerade Major masquerading table                                        
1124 netstat       Network statistics                                              
1125 raw           raw device statistics                                           
1126 route         Kernel routing table                                            
1127 rpc           Directory containing rpc info                                   
1128 rt_cache      Routing cache                                                   
1129 snmp          SNMP data                                                       
1130 sockstat      Socket statistics                                               
1131 tcp           TCP  sockets                                                    
1132 udp           UDP sockets                                                     
1133 unix          UNIX domain sockets                                             
1134 wireless      Wireless interface data (Wavelan etc)                           
1135 igmp          IP multicast addresses, which this host joined                  
1136 psched        Global packet scheduler parameters.                             
1137 netlink       List of PF_NETLINK sockets                                      
1138 ip_mr_vifs    List of multicast virtual interfaces                            
1139 ip_mr_cache   List of multicast routing cache                                 
1140..............................................................................
1141
1142You can  use  this  information  to see which network devices are available in
1143your system and how much traffic was routed over those devices:
1144
1145  > cat /proc/net/dev 
1146  Inter-|Receive                                                   |[... 
1147   face |bytes    packets errs drop fifo frame compressed multicast|[... 
1148      lo:  908188   5596     0    0    0     0          0         0 [...         
1149    ppp0:15475140  20721   410    0    0   410          0         0 [...  
1150    eth0:  614530   7085     0    0    0     0          0         1 [... 
1151   
1152  ...] Transmit 
1153  ...] bytes    packets errs drop fifo colls carrier compressed 
1154  ...]  908188     5596    0    0    0     0       0          0 
1155  ...] 1375103    17405    0    0    0     0       0          0 
1156  ...] 1703981     5535    0    0    0     3       0          0 
1157
1158In addition, each Channel Bond interface has its own directory.  For
1159example, the bond0 device will have a directory called /proc/net/bond0/.
1160It will contain information that is specific to that bond, such as the
1161current slaves of the bond, the link status of the slaves, and how
1162many times the slaves link has failed.
1163
11641.5 SCSI info
1165-------------
1166
1167If you  have  a  SCSI  host adapter in your system, you'll find a subdirectory
1168named after  the driver for this adapter in /proc/scsi. You'll also see a list
1169of all recognized SCSI devices in /proc/scsi:
1170
1171  >cat /proc/scsi/scsi 
1172  Attached devices: 
1173  Host: scsi0 Channel: 00 Id: 00 Lun: 00 
1174    Vendor: IBM      Model: DGHS09U          Rev: 03E0 
1175    Type:   Direct-Access                    ANSI SCSI revision: 03 
1176  Host: scsi0 Channel: 00 Id: 06 Lun: 00 
1177    Vendor: PIONEER  Model: CD-ROM DR-U06S   Rev: 1.04 
1178    Type:   CD-ROM                           ANSI SCSI revision: 02 
1179
1180
1181The directory  named  after  the driver has one file for each adapter found in
1182the system.  These  files  contain information about the controller, including
1183the used  IRQ  and  the  IO  address range. The amount of information shown is
1184dependent on  the adapter you use. The example shows the output for an Adaptec
1185AHA-2940 SCSI adapter:
1186
1187  > cat /proc/scsi/aic7xxx/0 
1188   
1189  Adaptec AIC7xxx driver version: 5.1.19/3.2.4 
1190  Compile Options: 
1191    TCQ Enabled By Default : Disabled 
1192    AIC7XXX_PROC_STATS     : Disabled 
1193    AIC7XXX_RESET_DELAY    : 5 
1194  Adapter Configuration: 
1195             SCSI Adapter: Adaptec AHA-294X Ultra SCSI host adapter 
1196                             Ultra Wide Controller 
1197      PCI MMAPed I/O Base: 0xeb001000 
1198   Adapter SEEPROM Config: SEEPROM found and used. 
1199        Adaptec SCSI BIOS: Enabled 
1200                      IRQ: 10 
1201                     SCBs: Active 0, Max Active 2, 
1202                           Allocated 15, HW 16, Page 255 
1203               Interrupts: 160328 
1204        BIOS Control Word: 0x18b6 
1205     Adapter Control Word: 0x005b 
1206     Extended Translation: Enabled 
1207  Disconnect Enable Flags: 0xffff 
1208       Ultra Enable Flags: 0x0001 
1209   Tag Queue Enable Flags: 0x0000 
1210  Ordered Queue Tag Flags: 0x0000 
1211  Default Tag Queue Depth: 8 
1212      Tagged Queue By Device array for aic7xxx host instance 0: 
1213        {255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255} 
1214      Actual queue depth per device for aic7xxx host instance 0: 
1215        {1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1} 
1216  Statistics: 
1217  (scsi0:0:0:0) 
1218    Device using Wide/Sync transfers at 40.0 MByte/sec, offset 8 
1219    Transinfo settings: current(12/8/1/0), goal(12/8/1/0), user(12/15/1/0) 
1220    Total transfers 160151 (74577 reads and 85574 writes) 
1221  (scsi0:0:6:0) 
1222    Device using Narrow/Sync transfers at 5.0 MByte/sec, offset 15 
1223    Transinfo settings: current(50/15/0/0), goal(50/15/0/0), user(50/15/0/0) 
1224    Total transfers 0 (0 reads and 0 writes) 
1225
1226
12271.6 Parallel port info in /proc/parport
1228---------------------------------------
1229
1230The directory  /proc/parport  contains information about the parallel ports of
1231your system.  It  has  one  subdirectory  for  each port, named after the port
1232number (0,1,2,...).
1233
1234These directories contain the four files shown in Table 1-10.
1235
1236
1237Table 1-10: Files in /proc/parport
1238..............................................................................
1239 File      Content                                                             
1240 autoprobe Any IEEE-1284 device ID information that has been acquired.         
1241 devices   list of the device drivers using that port. A + will appear by the
1242           name of the device currently using the port (it might not appear
1243           against any). 
1244 hardware  Parallel port's base address, IRQ line and DMA channel.             
1245 irq       IRQ that parport is using for that port. This is in a separate
1246           file to allow you to alter it by writing a new value in (IRQ
1247           number or none). 
1248..............................................................................
1249
12501.7 TTY info in /proc/tty
1251-------------------------
1252
1253Information about  the  available  and actually used tty's can be found in the
1254directory /proc/tty.You'll  find  entries  for drivers and line disciplines in
1255this directory, as shown in Table 1-11.
1256
1257
1258Table 1-11: Files in /proc/tty
1259..............................................................................
1260 File          Content                                        
1261 drivers       list of drivers and their usage                
1262 ldiscs        registered line disciplines                    
1263 driver/serial usage statistic and status of single tty lines 
1264..............................................................................
1265
1266To see  which  tty's  are  currently in use, you can simply look into the file
1267/proc/tty/drivers:
1268
1269  > cat /proc/tty/drivers 
1270  pty_slave            /dev/pts      136   0-255 pty:slave 
1271  pty_master           /dev/ptm      128   0-255 pty:master 
1272  pty_slave            /dev/ttyp       3   0-255 pty:slave 
1273  pty_master           /dev/pty        2   0-255 pty:master 
1274  serial               /dev/cua        5   64-67 serial:callout 
1275  serial               /dev/ttyS       4   64-67 serial 
1276  /dev/tty0            /dev/tty0       4       0 system:vtmaster 
1277  /dev/ptmx            /dev/ptmx       5       2 system 
1278  /dev/console         /dev/console    5       1 system:console 
1279  /dev/tty             /dev/tty        5       0 system:/dev/tty 
1280  unknown              /dev/tty        4    1-63 console 
1281
1282
12831.8 Miscellaneous kernel statistics in /proc/stat
1284-------------------------------------------------
1285
1286Various pieces   of  information about  kernel activity  are  available in the
1287/proc/stat file.  All  of  the numbers reported  in  this file are  aggregates
1288since the system first booted.  For a quick look, simply cat the file:
1289
1290  > cat /proc/stat
1291  cpu  2255 34 2290 22625563 6290 127 456 0 0 0
1292  cpu0 1132 34 1441 11311718 3675 127 438 0 0 0
1293  cpu1 1123 0 849 11313845 2614 0 18 0 0 0
1294  intr 114930548 113199788 3 0 5 263 0 4 [... lots more numbers ...]
1295  ctxt 1990473
1296  btime 1062191376
1297  processes 2915
1298  procs_running 1
1299  procs_blocked 0
1300  softirq 183433 0 21755 12 39 1137 231 21459 2263
1301
1302The very first  "cpu" line aggregates the  numbers in all  of the other "cpuN"
1303lines.  These numbers identify the amount of time the CPU has spent performing
1304different kinds of work.  Time units are in USER_HZ (typically hundredths of a
1305second).  The meanings of the columns are as follows, from left to right:
1306
1307- user: normal processes executing in user mode
1308- nice: niced processes executing in user mode
1309- system: processes executing in kernel mode
1310- idle: twiddling thumbs
1311- iowait: In a word, iowait stands for waiting for I/O to complete. But there
1312  are several problems:
1313  1. Cpu will not wait for I/O to complete, iowait is the time that a task is
1314     waiting for I/O to complete. When cpu goes into idle state for
1315     outstanding task io, another task will be scheduled on this CPU.
1316  2. In a multi-core CPU, the task waiting for I/O to complete is not running
1317     on any CPU, so the iowait of each CPU is difficult to calculate.
1318  3. The value of iowait field in /proc/stat will decrease in certain
1319     conditions.
1320  So, the iowait is not reliable by reading from /proc/stat.
1321- irq: servicing interrupts
1322- softirq: servicing softirqs
1323- steal: involuntary wait
1324- guest: running a normal guest
1325- guest_nice: running a niced guest
1326
1327The "intr" line gives counts of interrupts  serviced since boot time, for each
1328of the  possible system interrupts.   The first  column  is the  total of  all
1329interrupts serviced  including  unnumbered  architecture specific  interrupts;
1330each  subsequent column is the  total for that particular numbered interrupt.
1331Unnumbered interrupts are not shown, only summed into the total.
1332
1333The "ctxt" line gives the total number of context switches across all CPUs.
1334
1335The "btime" line gives  the time at which the  system booted, in seconds since
1336the Unix epoch.
1337
1338The "processes" line gives the number  of processes and threads created, which
1339includes (but  is not limited  to) those  created by  calls to the  fork() and
1340clone() system calls.
1341
1342The "procs_running" line gives the total number of threads that are
1343running or ready to run (i.e., the total number of runnable threads).
1344
1345The   "procs_blocked" line gives  the  number of  processes currently blocked,
1346waiting for I/O to complete.
1347
1348The "softirq" line gives counts of softirqs serviced since boot time, for each
1349of the possible system softirqs. The first column is the total of all
1350softirqs serviced; each subsequent column is the total for that particular
1351softirq.
1352
1353
13541.9 Ext4 file system parameters
1355-------------------------------
1356
1357Information about mounted ext4 file systems can be found in
1358/proc/fs/ext4.  Each mounted filesystem will have a directory in
1359/proc/fs/ext4 based on its device name (i.e., /proc/fs/ext4/hdc or
1360/proc/fs/ext4/dm-0).   The files in each per-device directory are shown
1361in Table 1-12, below.
1362
1363Table 1-12: Files in /proc/fs/ext4/<devname>
1364..............................................................................
1365 File            Content                                        
1366 mb_groups       details of multiblock allocator buddy cache of free blocks
1367..............................................................................
1368
13692.0 /proc/consoles
1370------------------
1371Shows registered system console lines.
1372
1373To see which character device lines are currently used for the system console
1374/dev/console, you may simply look into the file /proc/consoles:
1375
1376  > cat /proc/consoles
1377  tty0                 -WU (ECp)       4:7
1378  ttyS0                -W- (Ep)        4:64
1379
1380The columns are:
1381
1382  device               name of the device
1383  operations           R = can do read operations
1384                       W = can do write operations
1385                       U = can do unblank
1386  flags                E = it is enabled
1387                       C = it is preferred console
1388                       B = it is primary boot console
1389                       p = it is used for printk buffer
1390                       b = it is not a TTY but a Braille device
1391                       a = it is safe to use when cpu is offline
1392  major:minor          major and minor number of the device separated by a colon
1393
1394------------------------------------------------------------------------------
1395Summary
1396------------------------------------------------------------------------------
1397The /proc file system serves information about the running system. It not only
1398allows access to process data but also allows you to request the kernel status
1399by reading files in the hierarchy.
1400
1401The directory  structure  of /proc reflects the types of information and makes
1402it easy, if not obvious, where to look for specific data.
1403------------------------------------------------------------------------------
1404
1405------------------------------------------------------------------------------
1406CHAPTER 2: MODIFYING SYSTEM PARAMETERS
1407------------------------------------------------------------------------------
1408
1409------------------------------------------------------------------------------
1410In This Chapter
1411------------------------------------------------------------------------------
1412* Modifying kernel parameters by writing into files found in /proc/sys
1413* Exploring the files which modify certain parameters
1414* Review of the /proc/sys file tree
1415------------------------------------------------------------------------------
1416
1417
1418A very  interesting part of /proc is the directory /proc/sys. This is not only
1419a source  of  information,  it also allows you to change parameters within the
1420kernel. Be  very  careful  when attempting this. You can optimize your system,
1421but you  can  also  cause  it  to  crash.  Never  alter kernel parameters on a
1422production system.  Set  up  a  development machine and test to make sure that
1423everything works  the  way  you want it to. You may have no alternative but to
1424reboot the machine once an error has been made.
1425
1426To change  a  value,  simply  echo  the new value into the file. An example is
1427given below  in the section on the file system data. You need to be root to do
1428this. You  can  create  your  own  boot script to perform this every time your
1429system boots.
1430
1431The files  in /proc/sys can be used to fine tune and monitor miscellaneous and
1432general things  in  the operation of the Linux kernel. Since some of the files
1433can inadvertently  disrupt  your  system,  it  is  advisable  to  read  both
1434documentation and  source  before actually making adjustments. In any case, be
1435very careful  when  writing  to  any  of these files. The entries in /proc may
1436change slightly between the 2.1.* and the 2.2 kernel, so if there is any doubt
1437review the kernel documentation in the directory /usr/src/linux/Documentation.
1438This chapter  is  heavily  based  on the documentation included in the pre 2.2
1439kernels, and became part of it in version 2.2.1 of the Linux kernel.
1440
1441Please see: Documentation/sysctl/ directory for descriptions of these
1442entries.
1443
1444------------------------------------------------------------------------------
1445Summary
1446------------------------------------------------------------------------------
1447Certain aspects  of  kernel  behavior  can be modified at runtime, without the
1448need to  recompile  the kernel, or even to reboot the system. The files in the
1449/proc/sys tree  can  not only be read, but also modified. You can use the echo
1450command to write value into these files, thereby changing the default settings
1451of the kernel.
1452------------------------------------------------------------------------------
1453
1454------------------------------------------------------------------------------
1455CHAPTER 3: PER-PROCESS PARAMETERS
1456------------------------------------------------------------------------------
1457
14583.1 /proc/<pid>/oom_adj & /proc/<pid>/oom_score_adj- Adjust the oom-killer score
1459--------------------------------------------------------------------------------
1460
1461These file can be used to adjust the badness heuristic used to select which
1462process gets killed in out of memory conditions.
1463
1464The badness heuristic assigns a value to each candidate task ranging from 0
1465(never kill) to 1000 (always kill) to determine which process is targeted.  The
1466units are roughly a proportion along that range of allowed memory the process
1467may allocate from based on an estimation of its current memory and swap use.
1468For example, if a task is using all allowed memory, its badness score will be
14691000.  If it is using half of its allowed memory, its score will be 500.
1470
1471There is an additional factor included in the badness score: the current memory
1472and swap usage is discounted by 3% for root processes.
1473
1474The amount of "allowed" memory depends on the context in which the oom killer
1475was called.  If it is due to the memory assigned to the allocating task's cpuset
1476being exhausted, the allowed memory represents the set of mems assigned to that
1477cpuset.  If it is due to a mempolicy's node(s) being exhausted, the allowed
1478memory represents the set of mempolicy nodes.  If it is due to a memory
1479limit (or swap limit) being reached, the allowed memory is that configured
1480limit.  Finally, if it is due to the entire system being out of memory, the
1481allowed memory represents all allocatable resources.
1482
1483The value of /proc/<pid>/oom_score_adj is added to the badness score before it
1484is used to determine which task to kill.  Acceptable values range from -1000
1485(OOM_SCORE_ADJ_MIN) to +1000 (OOM_SCORE_ADJ_MAX).  This allows userspace to
1486polarize the preference for oom killing either by always preferring a certain
1487task or completely disabling it.  The lowest possible value, -1000, is
1488equivalent to disabling oom killing entirely for that task since it will always
1489report a badness score of 0.
1490
1491Consequently, it is very simple for userspace to define the amount of memory to
1492consider for each task.  Setting a /proc/<pid>/oom_score_adj value of +500, for
1493example, is roughly equivalent to allowing the remainder of tasks sharing the
1494same system, cpuset, mempolicy, or memory controller resources to use at least
149550% more memory.  A value of -500, on the other hand, would be roughly
1496equivalent to discounting 50% of the task's allowed memory from being considered
1497as scoring against the task.
1498
1499For backwards compatibility with previous kernels, /proc/<pid>/oom_adj may also
1500be used to tune the badness score.  Its acceptable values range from -16
1501(OOM_ADJUST_MIN) to +15 (OOM_ADJUST_MAX) and a special value of -17
1502(OOM_DISABLE) to disable oom killing entirely for that task.  Its value is
1503scaled linearly with /proc/<pid>/oom_score_adj.
1504
1505The value of /proc/<pid>/oom_score_adj may be reduced no lower than the last
1506value set by a CAP_SYS_RESOURCE process. To reduce the value any lower
1507requires CAP_SYS_RESOURCE.
1508
1509Caveat: when a parent task is selected, the oom killer will sacrifice any first
1510generation children with separate address spaces instead, if possible.  This
1511avoids servers and important system daemons from being killed and loses the
1512minimal amount of work.
1513
1514
15153.2 /proc/<pid>/oom_score - Display current oom-killer score
1516-------------------------------------------------------------
1517
1518This file can be used to check the current score used by the oom-killer is for
1519any given <pid>. Use it together with /proc/<pid>/oom_score_adj to tune which
1520process should be killed in an out-of-memory situation.
1521
1522
15233.3  /proc/<pid>/io - Display the IO accounting fields
1524-------------------------------------------------------
1525
1526This file contains IO statistics for each running process
1527
1528Example
1529-------
1530
1531test:/tmp # dd if=/dev/zero of=/tmp/test.dat &
1532[1] 3828
1533
1534test:/tmp # cat /proc/3828/io
1535rchar: 323934931
1536wchar: 323929600
1537syscr: 632687
1538syscw: 632675
1539read_bytes: 0
1540write_bytes: 323932160
1541cancelled_write_bytes: 0
1542
1543
1544Description
1545-----------
1546
1547rchar
1548-----
1549
1550I/O counter: chars read
1551The number of bytes which this task has caused to be read from storage. This
1552is simply the sum of bytes which this process passed to read() and pread().
1553It includes things like tty IO and it is unaffected by whether or not actual
1554physical disk IO was required (the read might have been satisfied from
1555pagecache)
1556
1557
1558wchar
1559-----
1560
1561I/O counter: chars written
1562The number of bytes which this task has caused, or shall cause to be written
1563to disk. Similar caveats apply here as with rchar.
1564
1565
1566syscr
1567-----
1568
1569I/O counter: read syscalls
1570Attempt to count the number of read I/O operations, i.e. syscalls like read()
1571and pread().
1572
1573
1574syscw
1575-----
1576
1577I/O counter: write syscalls
1578Attempt to count the number of write I/O operations, i.e. syscalls like
1579write() and pwrite().
1580
1581
1582read_bytes
1583----------
1584
1585I/O counter: bytes read
1586Attempt to count the number of bytes which this process really did cause to
1587be fetched from the storage layer. Done at the submit_bio() level, so it is
1588accurate for block-backed filesystems. <please add status regarding NFS and
1589CIFS at a later time>
1590
1591
1592write_bytes
1593-----------
1594
1595I/O counter: bytes written
1596Attempt to count the number of bytes which this process caused to be sent to
1597the storage layer. This is done at page-dirtying time.
1598
1599
1600cancelled_write_bytes
1601---------------------
1602
1603The big inaccuracy here is truncate. If a process writes 1MB to a file and
1604then deletes the file, it will in fact perform no writeout. But it will have
1605been accounted as having caused 1MB of write.
1606In other words: The number of bytes which this process caused to not happen,
1607by truncating pagecache. A task can cause "negative" IO too. If this task
1608truncates some dirty pagecache, some IO which another task has been accounted
1609for (in its write_bytes) will not be happening. We _could_ just subtract that
1610from the truncating task's write_bytes, but there is information loss in doing
1611that.
1612
1613
1614Note
1615----
1616
1617At its current implementation state, this is a bit racy on 32-bit machines: if
1618process A reads process B's /proc/pid/io while process B is updating one of
1619those 64-bit counters, process A could see an intermediate result.
1620
1621
1622More information about this can be found within the taskstats documentation in
1623Documentation/accounting.
1624
16253.4 /proc/<pid>/coredump_filter - Core dump filtering settings
1626---------------------------------------------------------------
1627When a process is dumped, all anonymous memory is written to a core file as
1628long as the size of the core file isn't limited. But sometimes we don't want
1629to dump some memory segments, for example, huge shared memory or DAX.
1630Conversely, sometimes we want to save file-backed memory segments into a core
1631file, not only the individual files.
1632
1633/proc/<pid>/coredump_filter allows you to customize which memory segments
1634will be dumped when the <pid> process is dumped. coredump_filter is a bitmask
1635of memory types. If a bit of the bitmask is set, memory segments of the
1636corresponding memory type are dumped, otherwise they are not dumped.
1637
1638The following 9 memory types are supported:
1639  - (bit 0) anonymous private memory
1640  - (bit 1) anonymous shared memory
1641  - (bit 2) file-backed private memory
1642  - (bit 3) file-backed shared memory
1643  - (bit 4) ELF header pages in file-backed private memory areas (it is
1644            effective only if the bit 2 is cleared)
1645  - (bit 5) hugetlb private memory
1646  - (bit 6) hugetlb shared memory
1647  - (bit 7) DAX private memory
1648  - (bit 8) DAX shared memory
1649
1650  Note that MMIO pages such as frame buffer are never dumped and vDSO pages
1651  are always dumped regardless of the bitmask status.
1652
1653  Note that bits 0-4 don't affect hugetlb or DAX memory. hugetlb memory is
1654  only affected by bit 5-6, and DAX is only affected by bits 7-8.
1655
1656The default value of coredump_filter is 0x33; this means all anonymous memory
1657segments, ELF header pages and hugetlb private memory are dumped.
1658
1659If you don't want to dump all shared memory segments attached to pid 1234,
1660write 0x31 to the process's proc file.
1661
1662  $ echo 0x31 > /proc/1234/coredump_filter
1663
1664When a new process is created, the process inherits the bitmask status from its
1665parent. It is useful to set up coredump_filter before the program runs.
1666For example:
1667
1668  $ echo 0x7 > /proc/self/coredump_filter
1669  $ ./some_program
1670
16713.5     /proc/<pid>/mountinfo - Information about mounts
1672--------------------------------------------------------
1673
1674This file contains lines of the form:
1675
167636 35 98:0 /mnt1 /mnt2 rw,noatime master:1 - ext3 /dev/root rw,errors=continue
1677(1)(2)(3)   (4)   (5)      (6)      (7)   (8) (9)   (10)         (11)
1678
1679(1) mount ID:  unique identifier of the mount (may be reused after umount)
1680(2) parent ID:  ID of parent (or of self for the top of the mount tree)
1681(3) major:minor:  value of st_dev for files on filesystem
1682(4) root:  root of the mount within the filesystem
1683(5) mount point:  mount point relative to the process's root
1684(6) mount options:  per mount options
1685(7) optional fields:  zero or more fields of the form "tag[:value]"
1686(8) separator:  marks the end of the optional fields
1687(9) filesystem type:  name of filesystem of the form "type[.subtype]"
1688(10) mount source:  filesystem specific information or "none"
1689(11) super options:  per super block options
1690
1691Parsers should ignore all unrecognised optional fields.  Currently the
1692possible optional fields are:
1693
1694shared:X  mount is shared in peer group X
1695master:X  mount is slave to peer group X
1696propagate_from:X  mount is slave and receives propagation from peer group X (*)
1697unbindable  mount is unbindable
1698
1699(*) X is the closest dominant peer group under the process's root.  If
1700X is the immediate master of the mount, or if there's no dominant peer
1701group under the same root, then only the "master:X" field is present
1702and not the "propagate_from:X" field.
1703
1704For more information on mount propagation see:
1705
1706  Documentation/filesystems/sharedsubtree.txt
1707
1708
17093.6     /proc/<pid>/comm  & /proc/<pid>/task/<tid>/comm
1710--------------------------------------------------------
1711These files provide a method to access a tasks comm value. It also allows for
1712a task to set its own or one of its thread siblings comm value. The comm value
1713is limited in size compared to the cmdline value, so writing anything longer
1714then the kernel's TASK_COMM_LEN (currently 16 chars) will result in a truncated
1715comm value.
1716
1717
17183.7     /proc/<pid>/task/<tid>/children - Information about task children
1719-------------------------------------------------------------------------
1720This file provides a fast way to retrieve first level children pids
1721of a task pointed by <pid>/<tid> pair. The format is a space separated
1722stream of pids.
1723
1724Note the "first level" here -- if a child has own children they will
1725not be listed here, one needs to read /proc/<children-pid>/task/<tid>/children
1726to obtain the descendants.
1727
1728Since this interface is intended to be fast and cheap it doesn't
1729guarantee to provide precise results and some children might be
1730skipped, especially if they've exited right after we printed their
1731pids, so one need to either stop or freeze processes being inspected
1732if precise results are needed.
1733
1734
17353.8     /proc/<pid>/fdinfo/<fd> - Information about opened file
1736---------------------------------------------------------------
1737This file provides information associated with an opened file. The regular
1738files have at least three fields -- 'pos', 'flags' and mnt_id. The 'pos'
1739represents the current offset of the opened file in decimal form [see lseek(2)
1740for details], 'flags' denotes the octal O_xxx mask the file has been
1741created with [see open(2) for details] and 'mnt_id' represents mount ID of
1742the file system containing the opened file [see 3.5 /proc/<pid>/mountinfo
1743for details].
1744
1745A typical output is
1746
1747        pos:    0
1748        flags:  0100002
1749        mnt_id: 19
1750
1751All locks associated with a file descriptor are shown in its fdinfo too.
1752
1753lock:       1: FLOCK  ADVISORY  WRITE 359 00:13:11691 0 EOF
1754
1755The files such as eventfd, fsnotify, signalfd, epoll among the regular pos/flags
1756pair provide additional information particular to the objects they represent.
1757
1758        Eventfd files
1759        ~~~~~~~~~~~~~
1760        pos:    0
1761        flags:  04002
1762        mnt_id: 9
1763        eventfd-count:  5a
1764
1765        where 'eventfd-count' is hex value of a counter.
1766
1767        Signalfd files
1768        ~~~~~~~~~~~~~~
1769        pos:    0
1770        flags:  04002
1771        mnt_id: 9
1772        sigmask:        0000000000000200
1773
1774        where 'sigmask' is hex value of the signal mask associated
1775        with a file.
1776
1777        Epoll files
1778        ~~~~~~~~~~~
1779        pos:    0
1780        flags:  02
1781        mnt_id: 9
1782        tfd:        5 events:       1d data: ffffffffffffffff
1783
1784        where 'tfd' is a target file descriptor number in decimal form,
1785        'events' is events mask being watched and the 'data' is data
1786        associated with a target [see epoll(7) for more details].
1787
1788        Fsnotify files
1789        ~~~~~~~~~~~~~~
1790        For inotify files the format is the following
1791
1792        pos:    0
1793        flags:  02000000
1794        inotify wd:3 ino:9e7e sdev:800013 mask:800afce ignored_mask:0 fhandle-bytes:8 fhandle-type:1 f_handle:7e9e0000640d1b6d
1795
1796        where 'wd' is a watch descriptor in decimal form, ie a target file
1797        descriptor number, 'ino' and 'sdev' are inode and device where the
1798        target file resides and the 'mask' is the mask of events, all in hex
1799        form [see inotify(7) for more details].
1800
1801        If the kernel was built with exportfs support, the path to the target
1802        file is encoded as a file handle.  The file handle is provided by three
1803        fields 'fhandle-bytes', 'fhandle-type' and 'f_handle', all in hex
1804        format.
1805
1806        If the kernel is built without exportfs support the file handle won't be
1807        printed out.
1808
1809        If there is no inotify mark attached yet the 'inotify' line will be omitted.
1810
1811        For fanotify files the format is
1812
1813        pos:    0
1814        flags:  02
1815        mnt_id: 9
1816        fanotify flags:10 event-flags:0
1817        fanotify mnt_id:12 mflags:40 mask:38 ignored_mask:40000003
1818        fanotify ino:4f969 sdev:800013 mflags:0 mask:3b ignored_mask:40000000 fhandle-bytes:8 fhandle-type:1 f_handle:69f90400c275b5b4
1819
1820        where fanotify 'flags' and 'event-flags' are values used in fanotify_init
1821        call, 'mnt_id' is the mount point identifier, 'mflags' is the value of
1822        flags associated with mark which are tracked separately from events
1823        mask. 'ino', 'sdev' are target inode and device, 'mask' is the events
1824        mask and 'ignored_mask' is the mask of events which are to be ignored.
1825        All in hex format. Incorporation of 'mflags', 'mask' and 'ignored_mask'
1826        does provide information about flags and mask used in fanotify_mark
1827        call [see fsnotify manpage for details].
1828
1829        While the first three lines are mandatory and always printed, the rest is
1830        optional and may be omitted if no marks created yet.
1831
1832        Timerfd files
1833        ~~~~~~~~~~~~~
1834
1835        pos:    0
1836        flags:  02
1837        mnt_id: 9
1838        clockid: 0
1839        ticks: 0
1840        settime flags: 01
1841        it_value: (0, 49406829)
1842        it_interval: (1, 0)
1843
1844        where 'clockid' is the clock type and 'ticks' is the number of the timer expirations
1845        that have occurred [see timerfd_create(2) for details]. 'settime flags' are
1846        flags in octal form been used to setup the timer [see timerfd_settime(2) for
1847        details]. 'it_value' is remaining time until the timer exiration.
1848        'it_interval' is the interval for the timer. Note the timer might be set up
1849        with TIMER_ABSTIME option which will be shown in 'settime flags', but 'it_value'
1850        still exhibits timer's remaining time.
1851
18523.9     /proc/<pid>/map_files - Information about memory mapped files
1853---------------------------------------------------------------------
1854This directory contains symbolic links which represent memory mapped files
1855the process is maintaining.  Example output:
1856
1857     | lr-------- 1 root root 64 Jan 27 11:24 333c600000-333c620000 -> /usr/lib64/ld-2.18.so
1858     | lr-------- 1 root root 64 Jan 27 11:24 333c81f000-333c820000 -> /usr/lib64/ld-2.18.so
1859     | lr-------- 1 root root 64 Jan 27 11:24 333c820000-333c821000 -> /usr/lib64/ld-2.18.so
1860     | ...
1861     | lr-------- 1 root root 64 Jan 27 11:24 35d0421000-35d0422000 -> /usr/lib64/libselinux.so.1
1862     | lr-------- 1 root root 64 Jan 27 11:24 400000-41a000 -> /usr/bin/ls
1863
1864The name of a link represents the virtual memory bounds of a mapping, i.e.
1865vm_area_struct::vm_start-vm_area_struct::vm_end.
1866
1867The main purpose of the map_files is to retrieve a set of memory mapped
1868files in a fast way instead of parsing /proc/<pid>/maps or
1869/proc/<pid>/smaps, both of which contain many more records.  At the same
1870time one can open(2) mappings from the listings of two processes and
1871comparing their inode numbers to figure out which anonymous memory areas
1872are actually shared.
1873
18743.10    /proc/<pid>/timerslack_ns - Task timerslack value
1875---------------------------------------------------------
1876This file provides the value of the task's timerslack value in nanoseconds.
1877This value specifies a amount of time that normal timers may be deferred
1878in order to coalesce timers and avoid unnecessary wakeups.
1879
1880This allows a task's interactivity vs power consumption trade off to be
1881adjusted.
1882
1883Writing 0 to the file will set the tasks timerslack to the default value.
1884
1885Valid values are from 0 - ULLONG_MAX
1886
1887An application setting the value must have PTRACE_MODE_ATTACH_FSCREDS level
1888permissions on the task specified to change its timerslack_ns value.
1889
1890
1891------------------------------------------------------------------------------
1892Configuring procfs
1893------------------------------------------------------------------------------
1894
18954.1     Mount options
1896---------------------
1897
1898The following mount options are supported:
1899
1900        hidepid=        Set /proc/<pid>/ access mode.
1901        gid=            Set the group authorized to learn processes information.
1902
1903hidepid=0 means classic mode - everybody may access all /proc/<pid>/ directories
1904(default).
1905
1906hidepid=1 means users may not access any /proc/<pid>/ directories but their
1907own.  Sensitive files like cmdline, sched*, status are now protected against
1908other users.  This makes it impossible to learn whether any user runs
1909specific program (given the program doesn't reveal itself by its behaviour).
1910As an additional bonus, as /proc/<pid>/cmdline is unaccessible for other users,
1911poorly written programs passing sensitive information via program arguments are
1912now protected against local eavesdroppers.
1913
1914hidepid=2 means hidepid=1 plus all /proc/<pid>/ will be fully invisible to other
1915users.  It doesn't mean that it hides a fact whether a process with a specific
1916pid value exists (it can be learned by other means, e.g. by "kill -0 $PID"),
1917but it hides process' uid and gid, which may be learned by stat()'ing
1918/proc/<pid>/ otherwise.  It greatly complicates an intruder's task of gathering
1919information about running processes, whether some daemon runs with elevated
1920privileges, whether other user runs some sensitive program, whether other users
1921run any program at all, etc.
1922
1923gid= defines a group authorized to learn processes information otherwise
1924prohibited by hidepid=.  If you use some daemon like identd which needs to learn
1925information about processes information, just add identd to this group.
1926
lxr.linux.no kindly hosted by Redpill Linpro AS, provider of Linux consulting and operations services since 1995.